Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4010 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.4948. Min Act: -0.1700
Data Index: 2229450 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.3698. Min Act: -0.1700
Data Index: 6793084 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.2448. Min Act: -0.1700
Data Index: 5144847 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.1823. Min Act: -0.1700
Data Index: 8517173 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.1198. Min Act: -0.1700
Data Index: 2544667 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.0885. Min Act: -0.1700
Data Index: 4240696 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.0260. Min Act: -0.1700
Data Index: 3758776 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4948. Min Range: -5.4948
Max Act: 4.9635. Min Act: -0.1700
Data Index: 7333132 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4948. Min Range: -5.4948
Max Act: 4.9635. Min Act: -0.1700
Data Index: 7961799 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4948. Min Range: -5.4948
Max Act: 4.9010. Min Act: -0.1700
Data Index: 2688542 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4948. Min Range: -5.4948
Max Act: 4.9010. Min Act: -0.1700
Data Index: 7751578 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4948. Min Range: -5.4948
Max Act: 4.9010. Min Act: -0.1700
Data Index: 1287257 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4948. Min Range: -5.4948
Max Act: 4.9010. Min Act: -0.1700
Data Index: 4696773 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4948. Min Range: -5.4948
Max Act: 4.9010. Min Act: -0.1700
Data Index: 3560846 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4948. Min Range: -5.4948
Max Act: 4.8698. Min Act: -0.1700
Data Index: 7419039 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4948. Min Range: -5.4948
Max Act: 4.8698. Min Act: -0.1700
Data Index: 350091 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4948. Min Range: -5.4948
Max Act: 4.8698. Min Act: -0.1700
Data Index: 4755872 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4948. Min Range: -5.4948
Max Act: 4.8385. Min Act: -0.1700
Data Index: 1545419 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4948. Min Range: -5.4948
Max Act: 4.8385. Min Act: -0.1700
Data Index: 3459691 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4948. Min Range: -5.4948
Max Act: 4.8698. Min Act: -0.1700
Data Index: 7215525 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19